描述

This plugin registers exo as an AI provider in WordPress 7’s AI Client SDK and Connectors page.

exo connects all your devices into an AI cluster, enabling you to run frontier models locally. It exposes an OpenAI-compatible API that this plugin connects to.

Features:

Registers exo as a WordPress AI provider
OpenAI-compatible text generation via exo’s chat completions API
Auto-detect active models from your running exo cluster
Capability detection — displays model capabilities (Text, Code, Thinking, Vision) as badges
“Connect & Detect” / “Save & Re-detect” connector flow
Optional API key authentication with secure storage
Configurable endpoint URL (default: http://localhost:52415)
Settings integrated into WordPress 7’s Connectors page

Choosing a Model:

exo exposes every model in its catalog, but only models actively loaded on your cluster will respond. Use “Connect & Detect” on the Connectors page to discover which models are running.

Recommended — Instruct models produce clean, usable output for WordPress AI features (title generation, content suggestions, etc.):

Llama-3.2-3B-Instruct-8bit — ~3 GB, fast, great for short tasks
Meta-Llama-3.1-8B-Instruct-4bit — ~4 GB, good balance of speed and quality
Llama-3.3-70B-Instruct-4bit — ~35 GB, best quality, needs a larger cluster

Avoid — Reasoning/thinking models (Qwen3.5, DeepSeek, GLM, Nemotron-Nano) spend most tokens on internal chain-of-thought, producing slow responses with minimal visible output.

To load a model: exo run mlx-community/Llama-3.2-3B-Instruct-8bit

Requirements:

WordPress 7.0 or later
PHP 8.3 or later
A running exo cluster (see exo documentation)

Configuration

The plugin can be configured via the Connectors page or environment variables:

AIPRFOEX_ENDPOINT — exo API endpoint (default: http://localhost:52415)
AIPRFOEX_API_KEY — Optional API key for authentication
AIPRFOEX_MODEL — Model name to use (auto-detected if empty)

You can also define these as constants in wp-config.php.

屏幕截图

exo connector in the WordPress admin Connectors page, showing detected deployments and capabilities.

安装

Upload the ai-provider-for-exo folder to /wp-content/plugins/.
Activate the plugin through the Plugins menu in WordPress.
Go to Settings Connectors and configure your exo endpoint.
Start using AI features powered by your local exo cluster.

评价

此插件暂无评价。

贡献者及开发者

「AI Provider for exo」是开源软件。以下人员对此插件做出了贡献。

Per Sﾃｸderlind

帮助将「AI Provider for exo」翻译成简体中文。

对开发感兴趣吗?

您可以浏览代码，查看SVN仓库，或通过RSS订阅开发日志。

更新日志

1.0.3

Update npm development dependencies and resolve npm audit findings.

1.0.2

Fix AI plugin connector detection on WordPress 7.0 RC3 by pointing the hidden sentinel connector at its synced setting.

1.0.1

Added GitHub Actions workflow for deployment to WordPress.org.

1.0.0

Prefix all declarations, globals, and stored data for WordPress.org compliance.
Namespace changed to Aiprfoex.
Constants, options, REST namespace, script handles, and provider slug all use the aiprfoex prefix.
Environment variable names changed: AIPRFOEX_ENDPOINT, AIPRFOEX_API_KEY, AIPRFOEX_MODEL.
Add sanitize_callback to register_setting() for capabilities option.
Remove load_plugin_textdomain() — WordPress.org handles translations automatically.

0.3.0

Fix: resolve “RequestAuthenticationInterface instance not set” error in AI plugin title generation.
Fix: emulate multi-candidate responses — exo ignores OpenAI n parameter, now issues N sequential requests.
Implement createRequest() abstract method required by SDK.
Always register authentication even with empty API key (SDK requires an instance).
Whitelist localhost and non-standard ports for wp_safe_remote_request().
Prepend exo models to wpai_preferred_text_models filter for correct provider selection.
Increase request timeout to 300s for local inference.
Default max_tokens to 1024 to prevent unbounded reasoning in thinking models.
Add model selection guidance to documentation.

0.2.0

Add sentinel connector for WordPress AI plugin compatibility.
AI plugin now recognizes exo as a valid, configured provider.
Filter to hide internal sentinel connector from Connectors settings page.
Custom exo wordmark logo (40×40 square) for the Connectors page.
Fix: AI plugin showed “requires a valid AI Connector” despite exo being configured.

0.1.0

Initial release.
Register exo as a WordPress AI provider via the AI Client SDK.
OpenAI-compatible text generation through exo’s chat completions API.
Auto-detect active models from the exo cluster (REST endpoint: POST /exo/v1/detect).
Capability detection — captures and displays model capabilities (Text, Code, Thinking, Vision) as badges.
Connector settings UI with “Connect & Detect” / “Save & Re-detect” flow.
Detected active models displayed in a read-only panel with Refresh support.
Custom exo logo icon for the Connectors page.
Optional API key authentication with secure storage and masking.
Configurable endpoint URL (default: http://localhost:52415).
Environment variable and wp-config.php constant support (EXO_ENDPOINT, EXO_API_KEY, EXO_MODEL).
Full i18n support with Norwegian Bokmål (nb_NO) translation.